Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
/plugin marketplace add antohins/seo-tools-mcpnpx agentmods add plugins/antohins/seo-tools-mcp/xmlrivergit clone --depth 1 https://github.com/antohins/seo-tools-mcpGrade A, and why
xmlriver scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "xmlriver",
"displayName": "SEO Tools: XMLRiver (SERP + indexation)",
"version": "1.8.0",
"description": "Google & Yandex SERP, image/news/maps verticals, People Also Ask and URL indexation checks via XMLRiver. Read-only.",
"author": {
"name": "antohins",
"url": "https://github.com/antohins"
},
"homepage": "https://github.com/antohins/seo-tools-mcp/tree/main/servers/xmlriver#readme",
"repository": "https://github.com/antohins/seo-tools-mcp",
"license": "MIT",
"keywords": [
"seo",
"serp",
"google",
"yandex",
"xmlriver",
"indexation",
"rank-tracking"
],
"userConfig": {
"XMLRIVER_USER": {
"type": "string",
"title": "XMLRiver user ID",
"description": "Numeric user ID from your XMLRiver dashboard (xmlriver.com)."
},
"XMLRIVER_KEY": {
"type": "string",
"title": "XMLRiver API key",
"description": "API key from the same dashboard.",
"sensitive": true
}
}
}
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 37 lines scan A 892782edfd45
xmlriver is a plugin published in the GitHub repository antohins/seo-tools-mcp (3 stars, last pushed 4d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other plugins, from other repositories
yandex-webmaster-mcp
MCP server for Yandex Webmaster — query indexing, search queries, diagnostics and backlinks, and recrawl URLs, in plain language. Secretless PKCE login, read-only by default, TypeScript.
spook
Spook SEO tools over MCP: analyze any domain for winnable queries, 45+ free SEO tools, and SEO article generation/publishing.
google-search-console-cli marketplace
Plugin marketplace listing 1 plugin: google-search-console-cli.
yandex-direct
Управление Яндекс.Директ: кампании, объявления, ставки, OAuth.
claude-seo
Comprehensive SEO analysis plugin for Claude Code. 25 sub-skills (21 core + 1 orchestrator + 1 framework + 2 extension mirrors) and 18 sub-agents cover technical SEO, content quality, schema, sitemaps, Core Web Vitals, local SEO, backlinks, AI/GEO, ecommerce, hreflang, SXO, clustering, drift monitoring, and Google…
rampstack marketplace
RampStack Claude Skills: the website lifecycle as installable skills.